Collaborative filtering systems are widely used to provide personalised recommendations in various domains such as e-commerce, streaming services and social media platforms. Despite their effectiveness, these systems face significant challenges, including data sparsity, cold start problems, and popularity bias, which can limit their recommendation quality. This article proposes a novel approach to improve the performance of collaborative filtering systems by using Artificial Neural Networks (ANNs). We propose the formation of a network of experts, similar to an artificial neural network, whose members provide ratings for different items, thereby increasing the available data. We will analyse how this network can improve the quality of recommendations and how it can be integrated with neural networks to improve accuracy and efficiency.